No abstract

. Abstract-Software rejuvenation is a proactive software control technique that is used to improve a computing system performance when it suffers from software aging. In this paper, a two-granularity inspection-based software rejuvenation policy, which works as a closed-loop control technique, is proposed. This policy mitigates the negative impact of two-level software aging. The two levels considered are the user-level applications and the operating system. A Markov regenerative process model is constructed based on the system condition. We obtain the degradation rate of the application software and operating system from fault injection experiments. The diagnostic accuracy of the adopted monitor and analysis system, which is applied to inspect the application software and operating system, is considered as we provide the optimal rejuvenation strategies. Finally, the availability and the overall loss probability with their corresponding optimal inspection time intervals are obtained numerically based on the parameter values estimated from the experiments. Experimental results show that two-granularity software rejuvenation is much more effective than traditional single-level software rejuvenation. In our experimental study, when two-granularity software rejuvenation is used, the unavailability and the overall loss probability of the system were reduced by 17.9% and 2.65%, respectively, in comparison with the single-level rejuvenation.Index Terms-Diagnostic accuracy, Markov regenerative process (MRGP), multigranularity software aging, overall loss probability, software rejuvenation.

Service-based systems resource allocation in cloud computing is a key method of meeting service requests because service request workloads and resource demands change over time. When coping with dynamic fluctuating service requests and resource demands, adaptive resource allocation to ensure the quality of service (QoS) with the lowest resource consumption becomes challenging. In cloud computing, services share the same resource pool and compete for critical resources, such as CPU and memory resources. Because services need arbitrary resource combinations, focusing on a single resource may lead to excessive or deficient resource allocations or even service request failures. Due to the shared nature of cloud computing, QoS may be impacted by interference with co-hosted services. In this paper, we propose an adaptive control approach for resource allocation that adaptively reacts to dynamic request workloads and resource demands. The multivariable control is adopted to allocate multiple resources for multiple services according to the dynamic fluctuating requests and considers the interference between co-hosted services, thereby ensuring QoS even if the resource pool is insufficient. The comparative experiments show that the proposed approach can meet service requests and can improve resource utilization regardless of whether the resource pool is sufficient. INDEX TERMS Adaptive resource allocation, cloud computing, multivariable control, QoS. I. INTRODUCTION

No abstract

No abstract